Summary
This systematic review of 168 publications examines 3D modelling approaches in precision agriculture, synthesising evidence on sensor technologies (LiDAR, RGB, RGB-D), deployment platforms (UAVs, UGVs, robotic systems), and data processing methods. Applications are classified into crop phenotyping, machinery navigation, and autonomous field operations such as harvesting and pruning. The authors identify widespread adoption of AI-based processing alongside persistent challenges in sensor robustness, multisensor integration, and scalability of large 3D datasets.
Regional applicability
The findings apply broadly to UK precision agriculture contexts, as sensor technologies and platforms reviewed are globally available and independent of geography. Adoption barriers (sensor cost, computational requirements, technical expertise) and opportunities for autonomous operations are relevant to UK farm businesses considering precision technology investment, though regional validation and integration with UK farm management practices would be needed.
Key measures
Frequency and classification of 3D data types and sensing technologies; sensor platforms and application environments; data registration and processing techniques; application categories (phenotyping, navigation, field operations); adoption trends of AI-based methods.
Outcomes reported
The review synthesises 168 peer-reviewed publications on 3D modelling approaches in precision agriculture, categorising applications into crop phenotyping, machinery navigation, and field operations. It identifies dominant sensor types (LiDAR, RGB, RGB-D), deployment platforms (UAVs, UGVs, robotic systems), data processing methods, and key implementation challenges.
Topic tags
Dig deeper with Pulse AI.
Ask about this record, its theme or its relevance to UK farming and policy. Pulse AI uses selected catalogue evidence and cites the sources it draws on.